wealth_advisory_wealth_tax_loss_harvest

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true, readOnlyHint=false, openWorldHint=true, and idempotentHint=false, so the description only needs to add context. It does add one useful operational fact: the action routes through the domain-agent dispatcher under JWT, tenant, and company scope (auth context). However, it fails to disclose that tax-loss harvesting can trigger real portfolio changes, sales, or taxable events, which the destructive/open-world flags strongly imply.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is compact (roughly four lines), front-loaded with the action invocation, and the Args section is tightly formatted. The opening sentence is somewhat redundant with the tool name, but there is no bloat or tangential content, so it earns a 4.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, open-world action with potential financial side effects, the description omits the action's behavioral semantics, the expected structure of 'inputs,' and any relationship to the wealth siblings. The output schema covers return values, but an agent still lacks enough context to invoke this safely and correctly; this is thin boilerplate for a high-risk tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description is the only source of parameter meaning. It does explain that message is a 'free-text objective' and inputs is an 'optional JSON string of structured inputs,' which is real added meaning. However, it stops short of describing the expected JSON shape for the tax-loss-harvest action or giving any example, leaving the key 'inputs' contract underspecified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The lead sentence 'Run the wealth_advisory domain agent action wealth_tax_loss_harvest' simply restates the tool name as a command and never explains what the action actually does (e.g., realizing capital losses to offset taxable gains). Among the wealth_advisory siblings (portfolio_drift, retirement_withdrawal, monte_carlo_retirement, kyc_risk_intake), there is no semantic content allowing an agent to differentiate this action's objective. Only routing mechanics are added, which is not domain purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives zero guidance on when to invoke this tool versus the five wealth_advisory siblings or the generic dispatch_domain_agent sibling. There are no conditions, exclusions, prerequisites, or alternative recommendations, so an agent must rely entirely on the action name to decide.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.